Unusual Reinforcement Learning
Our blog about reinforcement learning and its applications to legal reasoning.
-
Nov 7Lemma 3: AI alignment and legal enforceabilityGuardrails on protecting users from legal risk are underdeveloped
-
Oct 27Lemma 2: Do web search agents improve legal reasoning?Why web agents can’t make up for underlying gaps in model reasoning
-
Oct 20Lemma 1: Announcing LAURAIntroducing our LAURA benchmark preview